Tootfinder

Cool. https://news.ycombinator.com/item?id=45963780

Argh quick somebody cut up my credit cards. #TOTP #keytar
https://reverb.com/uk/item/91420591-yamaha-shs-10r-fm-keytar-red

John Kunze @… talking about #ARK at #swib25 referring to his 10 persistent myths about persistent identifiers

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 410236 nodes and 3356824 edges.
Tags: Economic, Commerce, Unweighted

I don't think there's a single non essential item that I've bought for myself in the past two months, which hasn't dropped in price once I've bought it lol.

An international group is organizing an observing campaign through the Citizen Science Working Group of the #LUMIO mission: LUMIO is an ESA space mission to observe lunar #impact flashes (LIFs) from space, on the lunar far side (#Geminid meteoroid stream, 13-15 Dec 2025. During the maximum of the stream, the number of visible impact flashes will be higher than during non-shower times, therefore there is a good chance of detecting at least some impact flashes.
Observations can be made using moderately-sized telescopes and a video camera. On the website https://lif.mi.imati.cnr.it/home_page.php there are now a recording of a thorough talk about the project and its slides at https://lif.mi.imati.cnr.it/open_item_page.php?item_idk=LDB-000000001 and slides about the preferred analysis software ALFI at https://lif.mi.imati.cnr.it/open_item_page.php?item_idk=LDB-000000002 -if you want to join in the LGC please sign on by 21 November.

I am not sure what aerodynamic rail supports are, but they sound fancy.
"Spain to cut Barcelona-Madrid high-speed train journey to 'under two hours'
Transport minister announces aerodynamic upgrades will enable top speed of 350 km/h"
https://www.

Spain to cut Barcelona-Madrid high-speed train journey to 'under two hours'
Transport minister announces aerodynamic upgrades will enable top speed of 350 km/h

Ex-libris, capturado nas obras completas de Luciano.
Aqui: https://dn720307.ca.archive.org/0/items/lucian01luci_0/lucian01luci_0.pdf

What the fuck? https://www.aliexpress.com/item/1005008515834537.html

So I've a medical thing that I need to buy once a month on Amazon and they cancelled my subscription delivery for it last time (but not the subscription itself), without telling me.
I tried to just order it for one time delivery, but the delivery date was a month out and they immediately cancelled my order.
My wife told me to use my developer brain—and yes, imagining a bug with some row in a database being in a fugue state, the exactly a month out delivery date being the biggest hint to something going into a default state when a calculation fails.
So I removed the subscription to the item (they make it hard to find where to do this).
Bingo: I can now order immediately for delivery in two days and for working subscrpition delivery.

We've seen some big news in outbreaks over the weekend with Marburg in Ethiopia and H5N5 in Washington, US.
See more on both below👇.
https://bsky.app/profile/altcdc.altgov.info/post/3m5rjz67als2a

Alt CDC (they/them) (@altcdc.altgov.info)
🦠Marburg in Ethiopia Ethiopia confirmed its first-ever outbreak, with 9 cases in Southern Ethiopia. Marburg virus causes severe hemorrhagic fever; it's in the same family as Ebola. It primarily spreads through contact with body fluids. There are no vaccines. https://africacdc.org/news-item/africa-cdc-statement-on-confirmed-marburg-virus-disease-in-jinka-southern-region-ethiopia/

Falls #Berlin|er Denkmalfans hier Angst haben, sich über die Feiertage zu langweilen, hätte ich hier die Einträge der Berliner Denkmalliste, für die es noch kein Wikidata-Item zu geben scheint (zumindest ist die P2424-Property noch nicht eingetragen):

Em um momento raro de benevolência, decidi eliminar o último item de uma das provas de amanhã, justamente o que era o mais difícil. Talvez milagres de Natal realmente existam rs.

This is really funny futuristic HN frontpage post reach HN frontpage and delivers gold satire 😅 https://news.ycombinator.com/item?id=46205632

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
Qihang Zhao, Zhongbo Sun, Xiaoyang Zheng, Xian Guo, Siyuan Wang, Zihan Liang, Mingcan Peng, Ben Chen, Chenyi Lei
https://arxiv.org/abs/2510.12604

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items' side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. However, these methods fail to account for the asymmetry between collaboration and content, nor th…

An $O(n\log n)$ Algorithm for Single-Item Capacitated Lot Sizing with a One-Breakpoint All-Units Discount and Non-Increasing Prices
Kleitos Papadopoulos
https://arxiv.org/abs/2510.11368

An $O(n\log n)$ Algorithm for Single-Item Capacitated Lot Sizing with a One-Breakpoint All-Units Discount and Non-Increasing Prices
This paper addresses the single-item capacitated lot sizing problem with a 1-breakpoint all-units quantity discount in a monotonic setting where the purchase prices are non-increasing over the planning horizon. For this case, we establish several novel properties of the optimal solution and develop a hybrid dynamic programming approach that maintains a compact representation of the solution space by storing only essential information about the states and using linear equations for intermediate …

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

from my link log —
A PostgreSQL developer's .psqlrc
https://news.ycombinator.com/item?id=23826037
saved 2020-07-13 https://dot…

huh, the cloud really did eat everything
[src: https://escholarship.org/uc/item/32d6m0d1]

Recovering screen pixels of another app in Android using a timimg side-channel attack. Crazy! https://social.lansky.name/@hn100/115377419606967864

I have a rough plan for a location already. I hope it isn't too crowded.
"Catalonia proposes 27 safe sites to host over 85,000 people for 2026 total solar eclipse"
https://www.catalannews.com/society-scienc

Catalonia proposes 27 safe sites to host over 85,000 people for 2026 total solar eclipse
Meteorological phenomenon takes place on August 12 at 8:30 pm, with most selected sites located in southern Catalonia

Critical Line Item With Tom Ravlic
Tom Ravlic FIPA has looked at complex issues in business, finance and politics for a range of publications over two decades...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/critical-line-item/

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Liang Li, Zhou Yang, Xiaofei Zhu
https://arxiv.org/abs/2510.10564 https://

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Sequential recommendation aims to predict the next item based on user interests in historical interaction sequences. Historical interaction sequences often contain irrelevant noisy items, which significantly hinders the performance of recommendation systems. Existing research employs unsupervised methods that indirectly identify item-granularity irrelevant noise by predicting the ground truth item. Since these methods lack explicit noise labels, they are prone to misidentify users' interested i…

Not even a city councillor standed up for our Sheppard Bike lanes
RIP
#biketo

Text-Based Approaches to Item Alignment to Content Standards in Large-Scale Reading & Writing Tests
Yanbin Fu, Hong Jiao, Tianyi Zhou, Robert W. Lissitz, Nan Zhang, Ming Li, Qingshu Xu, Sydney Peters
https://arxiv.org/abs/2509.26431

Text-Based Approaches to Item Alignment to Content Standards in Large-Scale Reading & Writing Tests
Aligning test items to content standards is a critical step in test development to collect validity evidence based on content. Item alignment has typically been conducted by human experts. This judgmental process can be subjective and time-consuming. This study investigated the performance of fine-tuned small language models (SLMs) for automated item alignment using data from a large-scale standardized reading and writing test for college admissions. Different SLMs were trained for alignment at…

Fair Division of Indivisible Items
Kevin Hsu
https://arxiv.org/abs/2510.12158 https://arxiv.org/pdf/2510.12158

Fair Division of Indivisible Items
We study the fair division of indivisible items. In the general model, the goal is to allocate $m$ indivisible items to $n$ agents while satisfying fairness criteria such as MMS, EF1, and EFX. We also study a recently-introduced graphical model that represents the fair division problem as a multigraph, in which vertices correspond to agents and edges to items. The graphical model stipulates that an item can have non-zero marginal utility to an agent only if its corresponding edge is incident to…

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

In #Wikimedia land, I created my first #Lua module in #WikimediaCommons:

This is surely going to be in a future RISKS Digest.
"This aspect of Helios’ design ensures that no two trustees could collude to determine the outcome of an election or the contents of individual votes on their own: all trustees must provide their decryption shares.
Unfortunately, one of the three trustees has irretrievably lost their private key [...]"

Falschinformationen können dazu führen, dass Klimaschutzmaßnahmen gezielt untergraben werden. Journalisten greifen daher häufig zu der Strategie, solche Falschinformationen direkt zu widerlegen. Forschungsergebnisse zeigen jedoch, dass diese auf den ersten Blick plausible Vorgehensweise nicht in allen Fällen wirksam ist. Unter bestimmten Bedingungen kann sie unbeabsichtigt sogar zur weiteren Verbreitung von Falschinformationen beitragen.

Efficient Bayesian Inference from Noisy Pairwise Comparisons
Till Aczel, Lucas Theis, Wattenhofer Roger
https://arxiv.org/abs/2510.09333 https://arxiv.org/…

Efficient Bayesian Inference from Noisy Pairwise Comparisons
Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more reliable but costly and noisy, as participants vary in expertise, attention, and diligence. Pairwise comparisons improve consistency, yet aggregating them into overall quality scores requires careful modeling. Bradley-Terry-based methods update item scores from comparisons, but existing approaches either ignore rater variability or lack convergence guarantees,…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Tjonge wat een staaltje Israel-propaganda was het item over de Kristallnacht herdenking in het NOS journaal.
Ik kan daar niet naar kijken zonder inwendig heel boos te worden over het misbruiken van zo'n terechte herdenking voor het heiligverklaren van alles wat Israel heet en Israel doet.
Marjolein Hogervorst: "Volgens Durlacher komt de kritiek op Israel voort uit het antisemitisme dat in ons land leeft".
Ik heb niet terug kunnen vinden dat ze dat zo gezegd hee…

Geweldig item van Lubach, hoe de fossiele autolobby Europa kapot maakt. Lobby tegen verbod op verbrandingsmotoren vanaf 2035 is krankzinnig. Kijken!
#EV #China #EU

It annoys me that replacing my IKEA "Högmodig" coffee carafe is possible, but only if I'm willing to travel to Dubai or India (but nowhere in Europe or America)

Während die #EUCommission unter #CDU-Führung versucht die Totalüberwachung unter dem Vorwand, Kinder vor sexuellen Angriffen zu schützen, für staatlichen Einsatz zu legalisieren fährt die #Totalüberwachung

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 410236 nodes and 3356824 edges.
Tags: Economic, Commerce, Unweighted

Imagine, you and three changeling companions, driving a sensible sedan during a race against two other teams: one driving a hot rod, the third one driving mum's lame minivan.
Your task is to collect one food item each from 10 diners all over New Jersey.
Easy?
Well, your driver refuses to speed even one mph over the speed limit and almost kidnaps 'accidentally' a very annoying changeling that was needlessly getting into your team's way.
1/3

eBike Nerdery
I suppose there's also this monster, which looks like a clone of the CYC Photon, but I can find no information about it https://www.aliexpress.us/item/3256809614522932.html

Aliexpress be like - this item is only $2!!! Act fast, it's the only one of 10,000 left. Special deal! Hurry!
*Adds to cart*
That'll be $27.53

Notable at Fri Dec 5th SFMTA engineering hearing:
👍 Item 1: Slow Golden Gate Ave gets concrete diverter
🙅‍♂️ Item 7: Kirkham neckdown to be removed and replaced by less effective traffic calming
https://www.sfmta.com/media/43965/download?inline

93 photos released from the Jeffrey Epstein estate (Dec. 12, 2025)
Usage Public Domain Mark 1.0Topics
Jeffrey Epstein
Item Size 63.6M
https://archive.org/details/house-oversight-034614
Photos originally hosted here:

93 photos released from the Jeffrey Epstein estate (Dec. 12, 2025) : Free Download, Borrow, and Streaming : Internet Archive
Photos originally hosted here:...

On Inherited Popularity Bias in Cold-Start Item Recommendation
Gregor Meehan, Johan Pauwels
https://arxiv.org/abs/2510.11402 https://arxiv.org/pdf/2510.114…

On Inherited Popularity Bias in Cold-Start Item Recommendation
Collaborative filtering (CF) recommender systems struggle with making predictions on unseen, or 'cold', items. Systems designed to address this challenge are often trained with supervision from warm CF models in order to leverage collaborative and content information from the available interaction data. However, since they learn to replicate the behavior of CF methods, cold-start models may therefore also learn to imitate their predictive biases. In this paper, we show that cold-start systems c…

This might become one of my next projects. Sounds very promising.
Building a Dedicated Diretta Link with Audiolinux on Raspberry Pi
by David Snyder
https://www.audiophi…

Building a Dedicated Diretta Link with Audiolinux on Raspberry Pi - Audiophile Foundation
This month's Tech Talk is provided courtesy of David Snyder, who has shared several presentations with the Audiophile Foundation on a range of digital audio topics from digital basics to network streaming. David has put together a comprehensive How-To g

I like how JC Penney is like, "Sure, we sent you the wrong item, but we're going to charge you $8 to return it. Because we can. Fuck you."
I hate Amazon, but I also shed no tears when most of these other shitty chains go bankrupt.
[Yes, it's free to return to the store, but that's not how I bought it in the first place and it's not the least bit convenient.]

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

/2
En zie daar het grote verschil dat Nieuwsuur maakt vandaag. Daar een lang item over een Israëlische vrouw em een Palestijnse man die Eem paar km uit elkaar wonen..
Achteraan ook bovenstaand stukje.
De bijeenkomst werd gehouden door de Israëlische ambassade en CJO.
Zeker zolang Israel genocide pleegt is het onbestaanbaar dat Schoof zich daar vertoont.
#RodeLijn #NLpol #Gaza

This is very exciting news 👀
@… https://social.lansky.name/@hn100/115375453553361259

yeah the oxford comma really solves all the problems nicely

Die Finanzierung für #Draconis ist gesichert
https://www.gameontabletop.com/cf5671/draconis.html#item-updates-85321

Train Stochastic Non Linear Coupled ODEs to Classify and Generate
Stefano Gagliani, Feliciano Giuseppe Pacifico, Lorenzo Chicchi, Duccio Fanelli, Diego Febbe, Lorenzo Buffoni, Raffaele Marino
https://arxiv.org/abs/2510.12286

Train Stochastic Non Linear Coupled ODEs to Classify and Generate
A general class of dynamical systems which can be trained to operate in classification and generation modes are introduced. A procedure is proposed to plant asymptotic stationary attractors of the deterministic model. Optimizing the dynamical system amounts to shaping the architecture of inter-nodes connection to steer the evolution towards the assigned equilibrium, as a function of the class to which the item - supplied as an initial condition - belongs to. Under the stochastic perspective, po…

OpenAI rolls out Instant Checkout to let users make single-item purchases directly in ChatGPT, starting with US Etsy sellers, and plans to add Shopify merchants (Ashley Capoot/CNBC)
https://www.cnbc.com/2025/09/29/chatgpt-instant-checkout-etsy-shopify.html…

Etsy pops 13% as OpenAI announces ChatGPT Instant Checkout for the shopping site
U.S. ChatGPT Plus, Pro and Free users can now make purchases through the chatbot

New #BandcampFriday purchase, Void Ecstasy by Nostalghia was available for free, but I paid $5 to support the artist and add it to my collection.
https://bandcamp.com/pmarg

Someone made a down detector for down detector https://news.ycombinator.com/item?id=45974012
Link: https://downdetectorsdowndetector.…

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

Catalonia bans access to natural areas in 91 municipalities until December 14 over African swine fever
https://www.catalannews.com/politics/item/african-swine-fever-outbreak-barcelona-catalonia-december-5-2025

Catalonia bans access to natural areas in 91 municipalities until December 14 over African swine fever
Entry to natural parks, forests, rivers, meadows, and farmland prohibited, though agricultural activity is allowed

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 400727 nodes and 3200440 edges.
Tags: Economic, Commerce, Unweighted

AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
Mingdai Yang, Nurendra Choudhary, Jiangshu Du, Edward W. Huang, Philip S. Yu, Karthik Subbian, Danai Kourta
https://arxiv.org/abs/2510.05598

AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-existent items and full-catalog ranking. Besides, a largely underexplored opportunity lies in leveraging LLMs'commonsense reasoning to capture user intent through substitute and complement relationships between items, which are usually implicit in datasets and difficult for traditional ID-based recommenders to capture. …

Online Allocation with Concave, Diminishing-Returns Objectives
Kalen Patton
https://arxiv.org/abs/2510.11266 https://arxiv.org/pdf/2510.11266

Online Allocation with Concave, Diminishing-Returns Objectives
Online resource allocation problems are central challenges in economics and computer science, modeling situations in which $n$ items arriving one at a time must each be immediately allocated among $m$ agents. In such problems, our objective is to maximize a monotone reward function $f(\mathbf{x})$ over the allocation vector $\mathbf{x} = (x_{ij})_{i, j}$, which describes the amount of each item given to each agent. In settings where $f$ is concave and has "diminishing returns" (monotone decreas…

Assembling GW231123 in Star Clusters through the Combination of Stellar Binary Evolution and Hierarchical Mergers: #BlackHole mergers: https://www.gssi.it/communication/news-events/item/26044-gssi-astrophysicists-reveal-the-role-of-star-clusters-in-black-hole-mergers

Aliexpress be like - this item is only $2!!! Act fast, it's the only one of 10,000 left. Special deal! Hurry!
*Adds to cart*
That'll be $27.53

Hallucinating Flows for Optimal Mechanisms
Marios Mertzanidis, Athina Terzoglou
https://arxiv.org/abs/2510.05474 https://arxiv.org/pdf/2510.05474

Hallucinating Flows for Optimal Mechanisms
Myerson's seminal characterization of the revenue-optimal auction for a single item \cite{myerson1981optimal} remains a cornerstone of mechanism design. However, generalizing this framework to multi-item settings has proven exceptionally challenging. Even under restrictive assumptions, closed-form characterizations of optimal mechanisms are rare and are largely confined to the single-agent case \cite{pavlov2011optimal,hart2017approximate, daskalakis2018transport, GIANNAKOPOULOS2018432}, departi…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Generation and annotation of item usage scenarios in e-commerce using large language models
Madoka Hagiri, Kazushi Okamoto, Koki Karube, Kei Harada, Atsushi Shibata
https://arxiv.org/abs/2510.07885

Generation and annotation of item usage scenarios in e-commerce using large language models
Complementary recommendations suggest combinations of useful items that play important roles in e-commerce. However, complementary relationships are often subjective and vary among individuals, making them difficult to infer from historical data. Unlike conventional history-based methods that rely on statistical co-occurrence, we focus on the underlying usage context that motivates item combinations. We hypothesized that people select complementary items by imagining specific usage scenarios an…

/2
En als derde item een indringend verslag van de ARD correspondent im dr VS die vorig jaar en nu Dearborn bezocht. Een stad met veel Arabische Amerikanen.
Aanrader!
(Ja ... Engels nasynchroniseren in Duits is een ramp. 🙈🙈)

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
Tiancheng Xing, Jerry Li, Yixuan Du, Xiyang Hu
https://arxiv.org/abs/2510.06732 https://

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First (RAF), a two-stage token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings while remaining hard to detect. Stage 1 uses Greedy Coordinate Gradient to shortlist candidate tokens at the current po…

Steil achterovergeslagen van dit doorwrochte item van #Lubach.
Ik wist dat het niet goed ging met de Europese auto-industrie maar het is echt 10 of 20 keer zo erg. En in plaats van bij te sturen rijden we alleen maar harder op het ravijn af.
https://

My local supermarket keeps changing how the product offers work...
Buy 4 for 3, cheapest item free
Buy 2 for some random reduced price
Buy 1 for some price that's reduced from whatever it was previously offered at.
Then there's loyalty card prices, which only apply to some items.
Why can't they just offer slightly lower prices across the range so everyone benefits without jumping through hoops?!

Causal Inspired Multi Modal Recommendation
Jie Yang, Chenyang Gu, Zixuan Liu
https://arxiv.org/abs/2510.12325 https://arxiv.org/pdf/2510.12325

Causal Inspired Multi Modal Recommendation
Multimodal recommender systems enhance personalized recommendations in e-commerce and online advertising by integrating visual, textual, and user-item interaction data. However, existing methods often overlook two critical biases: (i) modal confounding, where latent factors (e.g., brand style or product category) simultaneously drive multiple modalities and influence user preference, leading to spurious feature-preference associations; (ii) interaction bias, where genuine user preferences are m…

Space missions that could have been ... found this report - #Moon in the 1980s, visiting the poles where water ice was suspected. And using a lander to be built in LEO from components launched on three space shuttles. Not an option for Artemis III today, I'm afraid ...

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
Jingbo Yang, Bairu Hou, Wei Wei, Shiyu Chang, Yujia Bao
https://arxiv.org/abs/2510.06587 https://

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information extraction, and reasoning under constraints. We present WebDART, a general framework that enables a single LLM to handle such complex chores. WebDART (i) dynamically decomposes each objective into three focused subtasks: navigation, information extraction, and exe…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
Kaihong Li, Huichi Zhou, Bin Ma, Fangjun Huang
https://arxiv.org/abs/2509.24961 https://…

SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
Recommender systems (RS) are widely used in e-commerce for personalized suggestions, yet their openness makes them susceptible to shilling attacks, where adversaries inject fake behaviors to manipulate recommendations. Most existing defenses emphasize user-side behaviors while overlooking item-side features such as titles and descriptions that can expose malicious intent. To address this gap, we propose a two-stage detection framework that integrates item-side semantics via large language model…

"Speed cameras lead to 31% reduction in traffic accidents with injuries or deaths on Catalan roads"
https://www.catalannews.com/society-science/item/speed-cameras-lead-to-31-reduction-…

Speed cameras lead to 31% reduction in traffic accidents with injuries or deaths on Catalan roads
Government study says that 1,610 accidents have been prevented from 2002 to 2023

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
Andrei Chernov, Haroon Wahab, Oleg Novitskij
https://arxiv.org/abs/2510.12461 …

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, ins…

But I want summer time!
Who cares for light in the morning?
https://www.catalannews.com/society-science/item/spain-to-push-for-end-of-daylight-savings-at-european-level

Spain to push for end of daylight savings at European level
PM Sánchez argues clock changes have negative impact on health and barely saves energy

Optimal signals assignment for eBay View Item page
Matan Mandelbrod, Biwei Jiang, Giald Wagner, Tal Franji, Guy Feigenblat
https://arxiv.org/abs/2510.01198 https://

Optimal signals assignment for eBay View Item page
Signals are short textual or visual snippets displayed on the eBay View-Item (VI) page, providing additional, contextual information for users about the viewed item. The aim in displaying the signals is to facilitate intelligent purchase and to incentivise engagement. In this paper, we present two approaches for developing statistical models that optimally populate the VI page with signals. Both approaches were A/B tested, and yielded significant increase in business metrics.

Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
Amir Hossein Yari, Kalmit Kulkarni, Ahmad Raza Khan, Fajri Koto
https://arxiv.org/abs/2510.07061

Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
While automatic metrics drive progress in Machine Translation (MT) and Text Summarization (TS), existing metrics have been developed and validated almost exclusively for English and other high-resource languages. This narrow focus leaves Indian languages, spoken by over 1.5 billion people, largely overlooked, casting doubt on the universality of current evaluation practices. To address this gap, we introduce ITEM, a large-scale benchmark that systematically evaluates the alignment of 26 automat…

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Tingqiao Xu, Shaowei Yao, Chenhe Dong, Yiming Jin, Zerui Huang, Dan Ou, Haihong Tang
https://arxiv.org/abs/2510.11122

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Accurately modeling query-item relevance drives e-commerce ranking, yet long-tail, knowledge-heavy, and fast-evolving queries exceed parametric LLM coverage. External context (reviews, attribute encyclopedias, UGC) can help but is noisy, and single-pass latency and cost forbid any clean-then-summarize step. The model must, per query, judge relevance and decide whether to use, partially use, or ignore the context. DyKnow-RAG is a dynamic noisy-RAG framework built on Group Relative Policy Optimiz…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 400727 nodes and 3200440 edges.
Tags: Economic, Commerce, Unweighted

HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
Shuwei Chen, Jiajun Cui, Zhengqi Xu, Fan Zhang, Jiangke Fan, Teng Zhang, Xingxing Wang
https://arxiv.org/abs/2510.11100

HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence side features provide less granular interest representation compared to extensive non-sequential features, thereby impairing sequence modeling…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
https://arxiv.org/abs/2510.10556 htt…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential recommendation has recently emerged as a promising direction that exploits items' textual and visual features to enhance preference learning. However, there are still three key challenges: (i) how to reduce the semantic gap between different content modality representatio…

Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
Oscar Villemaud, Suryanarayana Sankagiri, Matthias Grossglauser
https://arxiv.org/abs/2510.01871 https:/…

Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
Ranking items is a central task in many information retrieval and recommender systems. User input for the ranking task often comes in the form of ratings on a coarse discrete scale. We ask whether it is possible to recover a fine-grained item ranking from such coarse-grained ratings. We model items as having scores and users as having thresholds; a user rates an item positively if the item's score exceeds the user's threshold. Although all users agree on the total item order, estimating that or…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Multi-Item-Query Attention for Stable Sequential Recommendation
Mingshi Xu, Haoren Zhu, Wilfred Siu Hung Ng
https://arxiv.org/abs/2509.24424 https://arxiv.…

Multi-Item-Query Attention for Stable Sequential Recommendation
The inherent instability and noise in user interaction data challenge sequential recommendation systems. Prevailing masked attention models, relying on a single query from the most recent item, are sensitive to this noise, reducing prediction reliability. We propose the Multi-Item-Query attention mechanism (MIQ-Attn) to enhance model stability and accuracy. MIQ-Attn constructs multiple diverse query vectors from user interactions, effectively mitigating noise and improving consistency. It is de…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 400727 nodes and 3200440 edges.
Tags: Economic, Commerce, Unweighted

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
KaiWen Wei, Kejun He, Xiaomian Kang, Jie Zhang, Yuming Yang, Jiang Zhong, He Bai, Junnan Zhu
https://arxiv.org/abs/2509.23649

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constrained by the reliance on purely autoregressive training. This approach focuses solely on predicting the next item while ignoring the rich internal structure of a user's interaction history, thus failing to grasp the underlying intent. To address this limitation, we propose Masked History Learning (MHL), a novel traini…

MTMD: A Multi-Task Multi-Domain Framework for Unified Ad Lightweight Ranking at Pinterest
Xiao Yang, Peifeng Yin, Abe Engle, Jinfeng Zhuang, Ling Leng
https://arxiv.org/abs/2510.09857

MTMD: A Multi-Task Multi-Domain Framework for Unified Ad Lightweight Ranking at Pinterest
The lightweight ad ranking layer, living after the retrieval stage and before the fine ranker, plays a critical role in the success of a cascaded ad recommendation system. Due to the fact that there are multiple optimization tasks depending on the ad domain, e.g., Click Through Rate (CTR) for click ads and Conversion Rate (CVR) for conversion ads, as well as multiple surfaces where an ad is served (home feed, search, or related item recommendation) with diverse ad products (shopping or standard…

Towards Long-Term User Welfare in Recommender Systems via Creator-Oriented Information Revelation
Xu Zhao, Xiaopeng Ye, Chen Xu, Weiran Shen, Jun Xu
https://arxiv.org/abs/2510.10511

Towards Long-Term User Welfare in Recommender Systems via Creator-Oriented Information Revelation
Improving the long-term user welfare (e.g., sustained user engagement) has become a central objective of recommender systems (RS). In real-world platforms, the creation behaviors of content creators plays a crucial role in shaping long-term welfare beyond short-term recommendation accuracy, making the effective steering of creator behavior essential to foster a healthier RS ecosystem. Existing works typically rely on re-ranking algorithms that heuristically adjust item exposure to steer creator…

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Chen Gao, Zixin Zhao, Lv Shao, Tong Liu
https://arxiv.org/abs/2510.11317

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Click-Through Rate (CTR) prediction, a cornerstone of modern recommender systems, has been dominated by discriminative models that react to past user behavior rather than proactively modeling user intent. Existing generative paradigms attempt to address this but suffer from critical limitations: Large Language Model (LLM) based methods create a semantic mismatch by forcing e-commerce signals into a linguistic space, while ID-based generation is constrained by item memorization and cold-start is…

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Yansong Wang, Qihui Lin, Junjie Huang, Tao Jia
https://arxiv.org/abs/2510.09129 https://

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, w…